Abstract
This article presents a method for the description of key points using simple statistics for regions controlled by neighboring key points to remedy the gap in existing descriptors. Usually, the existent descriptors such as speeded up robust features (SURF), Kaze, binary robust invariant scalable keypoints (BRISK), features from accelerated segment test (FAST), and oriented FAST and rotated BRIEF (ORB) can competently detect, describe, and match images in the presence of some artifacts such as blur, compression, and illumination. However, the performance and reliability of these descriptors decrease for some imaging variations such as point of view, zoom (scale), and rotation. The introduced description method improves image matching in the event of such distortions. It utilizes a contourlet-based detector to detect the strongest key points within a specified window size. The selected key points and their neighbors control the size and orientation of the surrounding regions, which are mapped on rectangular shapes using polar transformation. The resulting rectangular matrices are subjected to two-directional statistical operations that involve calculating the mean and standard deviation. Consequently, the descriptor obtained is invariant (translation, rotation, and scale) because of the two methods; the extraction of the region and the polar transformation techniques used in this paper. The description method introduced in this article is tested against well-established and well-known descriptors, such as SURF, Kaze, BRISK, FAST, and ORB, techniques using the standard OXFORD dataset. The presented methodology demonstrated its ability to improve the match between distorted images compared to other descriptors in the literature.
Highlights
Image matching is a challenging task in modern computer vision problems
This paper presents a key point-based descriptor that statistically compares key points in two images based on their corresponding neighbor regions
We introduced a simple descriptor based on statistical operations within the local neighborhood
Summary
Image matching is a challenging task in modern computer vision problems. Some applications, such as image structure from multiple frames and mapping creation for robotic applications, essentially use image matching for visualization purposes. Image matching can be defined as finding the projection of a given point from one image to another based on some features Such features can be described based on texture, color, or shape. They can be detected and extracted using different descriptors, such as scale-invariant feature transform (SIFT), (SURF), wavelet local feature descriptor (WLFD), and binary robust appearance and normal descriptors (BRAND). Descriptors should be characterized with some features to give an effective result They should not be affected by the noise, computationally efficient, and invariant to transformation, rotation, illumination, and scaling. Descriptors can be categorized into two types, edge detection-based descriptors and keypoints-based descriptors The former does not cost memory requirements, they lack detection accuracy because of occlusion and image perspectives.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
